Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Extension
    -0.08
    assertInstanceOf
    -0.07
     connectionString
    -0.07
     trous
    -0.07
     autoComplete
    -0.06
    一件
    -0.06
     const
    -0.06
    HIP
    -0.06
    _stand
    -0.06
    的学习
    -0.06
    POSITIVE LOGITS
    生态
    0.07
    ߊ
    0.07
    رفع
    0.07
    样本
    0.07
    ','%
    0.07
    Life
    0.06
    sanız
    0.06
     ])
    0.06
    -N
    0.06
     Aly
    0.06
    Act Density 0.491%

    No Known Activations